© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 48390
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doing right now

    np_acts-logits-general · gemini-2.5-flash-lite

    places where the author speaks in the first person—self-referential "I" statements or narration.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.39
     presupuesto
    -0.39
    Portale
    -0.39
    före
    -0.38
     kopling
    -0.37
     pendapatan
    -0.37
     quedarse
    -0.36
    fören
    -0.36
    harapkan
    -0.35
     mérite
    -0.35
    POSITIVE LOGITS
    帖最后由
    0.60
     للاسماء
    0.59
     tonight
    0.58
     сейчас
    0.57
     utafitiHapana
    0.56
    fillType
    0.53
    DockStyle
    0.52
     today
    0.51
    現在
    0.51
     propOrder
    0.51
    Activations Density 0.066%

    No Known Activations